Safety monitoring system of critical patient limb auxiliary exercise device

Abstract

The invention discloses a safety monitoring system of a critical patient limb auxiliary exercise device, and relates to the technical field of health monitoring, and the safety monitoring system comprises a vital sign collection module which collects vital sign data of a user in real time; the physical examination data analysis module is used for establishing a personalized health assessment model; the data processing and analyzing module is used for processing the vital sign data and the physical examination data in real time and comprehensively analyzing the current health condition based on a health assessment model; the health early warning module is used for evaluating the health condition of the user according to the analysis result and sending a health early warning signal when an abnormal condition is monitored; and the information display and feedback module is used for displaying the current information and feedback to the user. According to the method, the vital signs of the user are monitored in real time, comprehensive health assessment is carried out in combination with historical physical examination data, health changes are detected in time, the exercise risk is prevented, the health trend is predicted and the risk is assessed through a personalized health assessment model and machine learning, and the safety and the rehabilitation effect are helped to be improved.

Description

Technical Field

[0001] This invention relates to the field of health monitoring technology, specifically to a safety monitoring system for a limb assistive exercise device for critically ill patients. Background Technology

[0002] In the treatment of critically ill patients, the recovery of bodily functions and real-time monitoring of vital signs are crucial. With the continuous advancement of medical technology, more and more intelligent health monitoring systems are being applied in clinical practice to help doctors and patients conduct more accurate health management and risk assessment. However, traditional health monitoring systems mostly rely on single monitoring devices or only conduct diagnoses during hospitalization, which has certain limitations for long-term, continuous health management. Therefore, there is a need for a more comprehensive, accurate, and real-time updated health monitoring system that can dynamically assess and safely monitor the vital signs and health status of patients while they are performing limb-assisted exercises.

[0003] Currently, systems based on vital sign collection and historical physical examination data analysis are gradually becoming the mainstream of health monitoring. In order to better ensure the safety of critically ill patients, especially during rehabilitation processes such as limb-assisted exercises, health monitoring systems need to have the ability to update dynamically, acquire and analyze the latest vital sign data in real time, and combine personalized health assessment models to assess the user's health risks, ensuring that potential risks can be detected and warned in a timely manner, and providing timely health interventions. Summary of the Invention

[0004] To address the aforementioned technical problems, a safety monitoring system for a limb assistive exercise device for critically ill patients is provided. This technical solution resolves the problems described above.

[0005] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0006] A safety monitoring system for a limb assistive exercise device for critically ill patients includes: a vital signs acquisition module, a physical examination data analysis module, a data processing and analysis module, a health early warning module, and an information display and feedback module;

[0007] The vital signs acquisition module is used to collect the user's vital signs data in real time, including heart rate, blood oxygen saturation, and body temperature;

[0008] The physical examination data analysis module is used to receive and analyze users' historical physical examination data, and combine it with users' personal health records to establish a personalized health assessment model.

[0009] The data processing and analysis module is used to process vital sign data and physical examination data in real time, and to comprehensively analyze the current health status based on the health assessment model.

[0010] The health early warning module is used to assess the user's health status based on the analysis results and issue a health early warning signal when abnormalities are detected, reminding medical staff and patients to take measures.

[0011] The information display and feedback module is used to show users their current health status, warning information, and provide health advice to help them make health decisions.

[0012] Preferably, the vital signs acquisition module specifically includes:

[0013] Heart rate acquisition unit: Utilizes photoplethysmography (PPG) technology to monitor pulse fluctuations and acquire heart rate via an infrared sensor;

[0014] Blood oxygen saturation acquisition unit: It monitors and records blood oxygen saturation by measuring the difference in absorption between infrared and visible light, and monitors the user's oxygenation status in real time;

[0015] Body temperature acquisition unit: Based on a non-contact infrared temperature sensor, it monitors body surface temperature in real time;

[0016] Data acquisition and transmission unit: Based on Wi-Fi, the acquired vital sign data is transmitted in real time to the data processing and analysis module, which performs preliminary processing, filtering and calibration on the acquired physiological data to remove noise.

[0017] Preferably, the physical examination data analysis module specifically includes:

[0018] Historical physical examination data receiving unit: Receives users' historical physical examination data, including blood tests, imaging examinations, liver and kidney function, cholesterol levels, and blood sugar levels;

[0019] Personalized health assessment model building unit: Based on the user's historical physical examination data, health records and medical big data, a personalized health assessment model is built through machine learning algorithms. Based on the output of the health assessment model, the user's future health trend is predicted.

[0020] Health Risk Analysis Unit: Based on the user's future health trends, this unit analyzes the user's health data and uses artificial intelligence algorithms to assess the user's health risks.

[0021] Preferably, the step of establishing a personalized health assessment model based on the user's historical physical examination data, health records, and medical big data through machine learning algorithms, and predicting the user's future health trend based on the output of the health assessment model, specifically includes:

[0022] The formula for the health assessment model is as follows:

[0023] Y = B0 + B1X1 + B2X2 + ... + B n X n +∈

[0024] In the formula, Y represents the predicted health status score, X1 represents the input blood glucose characteristic, X2 represents the input cholesterol characteristic, and X... n For the nth feature B0, B1, B... n is the regression coefficient, and ∈ is the error term.

[0025] Preferably, the analysis of user health data based on future health trends, combined with artificial intelligence algorithms, to assess user health risks specifically includes:

[0026] A logistic regression machine learning classification model is used to assess user health risk based on predicted health trends. The risk assessment formula for logistic regression is as follows:

[0027]

[0028] In the formula, P(y=1|x) is the probability of the predicted event, y is the target variable, X is the input feature vector, w is the weight vector, x is a specific feature in the input feature vector X, b is the bias term, and exp is the exponential function.

[0029] Preferably, the data processing and analysis module specifically includes:

[0030] The dynamic update unit for health risk: Based on new physical examination data and health information, the health risk assessment model is dynamically updated to reflect the latest health status and trends. Based on the SGD online learning algorithm, the model is updated in real time when new data is received, and the model is retrained regularly with new data.

[0031] Results Interpretation and Feedback Unit: Generates a health report based on the results of the health risk assessment, and provides personalized health advice reports based on the user's lifestyle and dietary habits. The report output includes risk level, prediction of health status in the future period, and health intervention suggestions, including dietary adjustments, exercise recommendations, and regular physical examinations.

[0032] Preferably, the SGD-based online learning algorithm updates the model in real time upon receiving new data and periodically retrains the model using new data, specifically including:

[0033] The formula for the SGD online learning algorithm is as follows:

[0034]

[0035] In the formula, θ t These are the current model parameters, and δ is the learning rate, used to control the update step size. It is the gradient of the loss function L with respect to the model parameters θ, where θ t+1These are the updated model parameters;

[0036] Each time a new data point is received, the model is updated according to the above formula, so that the model can be adjusted in real time according to the new data. The model is also retrained in batches with new data periodically to update the entire model.

[0037] Regularly collect and organize new health data, input the new dataset into the model, perform batch retraining through the standard SGD process, and readjust the model parameters based on the new training data.

[0038] Preferably, the health early warning module specifically includes:

[0039] Health status assessment unit: Based on the results provided by the data processing and analysis module, including real-time vital signs data and historical physical examination data analysis results, assess the user's health status;

[0040] The abnormality detection and monitoring unit sets health thresholds and compares the collected vital sign data with the set normal range in real time. If the data exceeds the normal range, an early warning is triggered.

[0041] Early warning triggering unit: By interfacing with the anomaly detection unit, when an anomaly is detected, the early warning triggering unit will issue an early warning signal based on preset early warning standards and thresholds.

[0042] Preferably, the health warning module further includes:

[0043] Warning information transmission and notification unit: transmits warning information to patients, nursing staff and doctors, and notifies medical staff and patients of health warning information in real time according to the triggered warning level, and provides suggestions;

[0044] Warning Level Assessment Unit: Based on the user's health status and data analysis results, different warning levels are assigned to each warning situation, and each warning level corresponds to different response measures;

[0045] Response Response Recommendation Unit: Based on the type and urgency of the alert, this unit provides health advice, including temporary equipment shutdown, medical advice, and medication adjustments.

[0046] Preferably, the information display and feedback module specifically includes:

[0047] Decision Support Unit: Based on early warning information and health assessment results, it provides response measures and decision support;

[0048] Feedback and Interaction Unit: Interact with users, receive user feedback, adjust displayed content, and guide users to further understand the details of health advice;

[0049] Data update and synchronization unit: updates users' health status and early warning data in real time, while keeping synchronized with the data processing module and the health early warning module.

[0050] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0051] This invention proposes to conduct a comprehensive health assessment by real-time monitoring of users' vital signs and combining historical physical examination data. This allows for timely detection of health changes and prevention of exercise risks. Through personalized health assessment models and machine learning, it predicts health trends and assesses risks. The model is dynamically updated based on the SGD algorithm to ensure accuracy. A multi-level health early warning function promptly notifies medical staff and provides corresponding measures. A decision support and feedback mechanism provides users with personalized health advice, helping to improve safety and rehabilitation effects and optimize health management. Attached Figure Description

[0052] Figure 1 This is a system framework diagram of the present invention;

[0053] Figure 2 This is a diagram of the internal system framework of the physical examination data analysis module in this invention. Detailed Implementation

[0054] The following description is intended to disclose the invention so that those skilled in the art can implement it. The preferred embodiments described below are merely examples, and other obvious modifications will occur to those skilled in the art.

[0055] Reference Figure 1 As shown, a safety monitoring system for a limb assistive exercise device for critically ill patients includes: a vital signs acquisition module, a physical examination data analysis module, a data processing and analysis module, a health early warning module, and an information display and feedback module;

[0056] The vital signs acquisition module is used to collect the user's vital signs data in real time, including heart rate, blood oxygen saturation, and body temperature;

[0057] The physical examination data analysis module is used to receive and analyze users' historical physical examination data, and combine it with users' personal health records to establish a personalized health assessment model.

[0058] The data processing and analysis module is used to process vital sign data and physical examination data in real time, and to comprehensively analyze the current health status based on the health assessment model.

[0059] The health early warning module is used to assess the user's health status based on the analysis results and issue a health early warning signal when abnormalities are detected, reminding medical staff and patients to take measures.

[0060] The information display and feedback module is used to show users their current health status, warning information, and provide health advice to help them make health decisions.

[0061] The vital signs acquisition module specifically includes:

[0062] Heart rate acquisition unit: Utilizes photoplethysmography (PPG) technology to monitor pulse fluctuations and acquire heart rate via an infrared sensor;

[0063] Blood oxygen saturation acquisition unit: It monitors and records blood oxygen saturation by measuring the difference in absorption between infrared and visible light, and monitors the user's oxygenation status in real time;

[0064] Body temperature acquisition unit: Based on a non-contact infrared temperature sensor, it monitors body surface temperature in real time;

[0065] Data acquisition and transmission unit: Based on Wi-Fi, it transmits the collected vital sign data to the data processing and analysis module in real time, performs preliminary processing, filtering and calibration on the collected physiological data, and removes noise;

[0066] The module utilizes a combination of advanced sensor technologies and Wi-Fi data transmission to achieve real-time, contactless monitoring of users' vital signs, significantly improving monitoring accuracy and real-time performance. Its data processing and transmission units can eliminate noise interference, ensuring data accuracy and reliability.

[0067] Reference Figure 2 As shown, the physical examination data analysis module specifically includes:

[0068] Historical physical examination data receiving unit: Receives users' historical physical examination data, including blood tests, imaging examinations, liver and kidney function, cholesterol levels, and blood sugar levels;

[0069] Personalized health assessment model building unit: Based on the user's historical physical examination data, health records and medical big data, a personalized health assessment model is built through machine learning algorithms. Based on the output of the health assessment model, the user's future health trend is predicted.

[0070] Health Risk Analysis Unit: Based on the user's future health trends, analyze the user's health data and combine artificial intelligence algorithms to assess the user's health risks;

[0071] By combining users' historical physical examination data, health records, and big data analysis, the system can build personalized health assessment models and accurately predict users' future health trends. This personalized health assessment method based on machine learning algorithms makes health management more precise and closer to the user's specific situation.

[0072] Based on users' historical physical examination data, health records, and medical big data, a personalized health assessment model is built using machine learning algorithms. Based on the output of the health assessment model, the user's future health trends are predicted, specifically including:

[0073] The formula for the health assessment model is as follows:

[0074] Y = B0 + B1X1 + B2X2 + ... + B n X n +∈

[0075] In the formula, Y represents the predicted health status score, X1 represents the input blood glucose characteristic, X2 represents the input cholesterol characteristic, and X... n For the nth feature B0, B1, B... n is the regression coefficient, and ∈ is the error term.

[0076] Based on users' future health trends, the system analyzes users' health data and uses artificial intelligence algorithms to assess users' health risks, specifically including:

[0077] A logistic regression machine learning classification model is used to assess user health risk based on predicted health trends. The risk assessment formula for logistic regression is as follows:

[0078]

[0079] In the formula, P(y=1|x) is the probability of the event predicted by the model, y is the target variable, X is the input feature vector, w is the weight vector, x is a specific feature in the input feature vector X, b is the bias term, and exp is the exponential function.

[0080] By using machine learning algorithms, especially logistic regression models for health risk assessment, the system can predict and evaluate a user's future health risks based on real-time and historical data. This approach not only improves the accuracy of health predictions but also provides quantitative health risk assessments.

[0081] The data processing and analysis module specifically includes:

[0082] The dynamic update unit for health risk: Based on new physical examination data and health information, the health risk assessment model is dynamically updated to reflect the latest health status and trends. Based on the SGD online learning algorithm, the model is updated in real time when new data is received, and the model is retrained regularly with new data.

[0083] Results Interpretation and Feedback Unit: Generates a health report based on the results of the health risk assessment, and provides personalized health advice based on the user's lifestyle and dietary habits. The report output includes risk level, prediction of health status in the future period, and health intervention suggestions, including dietary adjustments, exercise recommendations, and regular physical examinations.

[0084] The SGD online learning algorithm updates the model in real time when new data is received and periodically retrains the model using new data. Specifically, this includes:

[0085] The formula for the SGD online learning algorithm is as follows:

[0086]

[0087] In the formula, θ t These are the current model parameters, and δ is the learning rate, used to control the update step size. It is the gradient of the loss function L with respect to the model parameters θ, where θ t+1 These are the updated model parameters;

[0088] Each time a new data point is received, the model is updated according to the above formula, so that the model can be adjusted in real time according to the new data. The model is also retrained in batches with new data periodically to update the entire model.

[0089] Regularly collect and organize new health data, input the new dataset into the model, perform batch retraining through the standard SGD process, and readjust the model parameters based on the new training data;

[0090] Based on the SGD online learning algorithm, the system can adjust the assessment model in real time when it receives new health data. This dynamic update mechanism not only ensures the adaptability of the system, but also enables regular batch retraining to continuously improve the accuracy and reliability of health assessment.

[0091] The health early warning module specifically includes:

[0092] Health status assessment unit: Based on the results provided by the data processing and analysis module, including real-time vital signs data and historical physical examination data analysis results, assess the user's health status;

[0093] The abnormality detection and monitoring unit sets health thresholds and compares the collected vital sign data with the set normal range in real time. If the data exceeds the normal range, an early warning is triggered.

[0094] Early warning triggering unit: By interfacing with the anomaly detection unit, when an anomaly is detected, the early warning triggering unit will issue an early warning signal based on preset early warning standards and thresholds.

[0095] The health early warning module also includes:

[0096] Warning information transmission and notification unit: transmits warning information to patients, nursing staff and doctors, and notifies medical staff and patients of health warning information in real time according to the triggered warning level, and provides suggestions;

[0097] Warning Level Assessment Unit: Based on the user's health status and data analysis results, different warning levels are assigned to each warning situation, and each warning level corresponds to different response measures;

[0098] Response Response Recommendation Unit: Based on the type and urgency of the alert, this unit provides health advice, including temporary equipment shutdown, medical advice, and medication adjustments.

[0099] The information display and feedback module specifically includes:

[0100] Decision Support Unit: Based on early warning information and health assessment results, it provides response measures and decision support;

[0101] Feedback and Interaction Unit: Interact with users, receive user feedback, adjust displayed content, and guide users to further understand the details of health advice;

[0102] Data update and synchronization unit: updates users' health status and early warning data in real time, while keeping synchronized with the data processing module and the health early warning module;

[0103] This module provides personalized health advice through decision support units and interactive feedback mechanisms, combining health assessment results with users' lifestyle habits. This feedback mechanism enables users to obtain health advice in real time during the monitoring process and make adjustments based on their own health status and feedback, thereby further optimizing their health management plan.

[0104] In summary, the advantages of this invention are:

[0105] The system can collect users' vital signs data such as heart rate, blood oxygen saturation, and body temperature in real time, and combine them with historical physical examination data to comprehensively assess users' health status. Through real-time data processing and analysis, it can detect changes in health status in a timely manner and prevent health risks caused by excessive or inappropriate exercise.

[0106] By combining users' health records, historical physical examination data, and medical big data, the system can build a personalized health assessment model for each user. Through machine learning algorithms, it can predict users' future health trends and assess their health risks. This personalized assessment method is more accurate than the traditional fixed standard and can provide targeted health advice.

[0107] The system, based on the SGD online learning algorithm, can update the health assessment model in real time each time new health data is received, reflecting the latest health status and trends. By dynamically updating the model, the system can ensure that it can adapt to changes in the user's health status, and by regularly using new data for batch retraining, the accuracy of health assessment can be continuously improved.

[0108] When the system detects abnormalities in a user's vital signs, it can automatically trigger a health alert and promptly transmit the alert information to medical staff and patients. Based on different health risk levels, the system provides corresponding coping measures and suggestions, such as adjusting exercise plans, medical advice, and medication adjustments.

[0109] The information display and feedback module provides users with personalized health advice through the decision support unit and adjusts the system output based on user feedback to further optimize health management. The system can not only display real-time health status, but also provide specific health intervention measures such as dietary adjustments and exercise suggestions to help users make more scientific and effective health decisions.

[0110] Through comprehensive health monitoring, risk assessment, and dynamic adjustments, the system significantly improves the safety of critically ill patients during limb-assisted exercise, reduces the number of emergencies caused by undetected health conditions, and helps patients recover faster and improve rehabilitation outcomes through the system's health intervention recommendations.

[0111] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the claimed invention. The scope of protection claimed by the appended claims and their equivalents is defined.

Claims

1. A safety monitoring system for a limb assistive exercise device for critically ill patients, characterized in that, include: The system includes a vital signs collection module, a physical examination data analysis module, a data processing and analysis module, a health early warning module, and an information display and feedback module. The vital signs acquisition module is used to collect the user's vital signs data in real time, including heart rate, blood oxygen saturation, and body temperature; The physical examination data analysis module is used to receive and analyze users' historical physical examination data, and combine it with users' personal health records to establish a personalized health assessment model. The data processing and analysis module is used to process vital sign data and physical examination data in real time, and to comprehensively analyze the current health status based on the health assessment model. The health early warning module is used to assess the user's health status based on the analysis results and issue a health early warning signal when abnormalities are detected, reminding medical staff and patients to take measures. The information display and feedback module is used to show users their current health status, warning information, and provide health advice to help them make health decisions.

2. The safety monitoring system for a limb assistive exercise device for critically ill patients according to claim 1, characterized in that, The vital signs acquisition module specifically includes: Heart rate acquisition unit: Utilizes photoplethysmography (PPG) technology to monitor pulse fluctuations and acquire heart rate via an infrared sensor; Blood oxygen saturation acquisition unit: It monitors and records blood oxygen saturation by measuring the difference in absorption between infrared and visible light, and monitors the user's oxygenation status in real time; Body temperature acquisition unit: Based on a non-contact infrared temperature sensor, it monitors body surface temperature in real time; Data acquisition and transmission unit: Based on Wi-Fi, the acquired vital sign data is transmitted in real time to the data processing and analysis module, which performs preliminary processing, filtering and calibration on the acquired physiological data to remove noise.

3. The safety monitoring system for a limb assistive exercise device for critically ill patients according to claim 2, characterized in that, The physical examination data analysis module specifically includes: Historical physical examination data receiving unit: Receives users' historical physical examination data, including blood tests, imaging examinations, liver and kidney function, cholesterol levels, and blood sugar levels; Personalized health assessment model building unit: Based on the user's historical physical examination data, health records and medical big data, a personalized health assessment model is built through machine learning algorithms. Based on the output of the health assessment model, the user's future health trend is predicted. Health Risk Analysis Unit: Based on the user's future health trends, this unit analyzes the user's health data and uses artificial intelligence algorithms to assess the user's health risks.

4. The safety monitoring system for a limb assistive exercise device for critically ill patients according to claim 3, characterized in that, Based on users' historical physical examination data, health records, and medical big data, a personalized health assessment model is established using machine learning algorithms. Based on the output of the health assessment model, specific future health trends of users are predicted. include: The formula for the health assessment model is as follows: Y=B0+B1X1+B2X2+…+B n X n +∈ In the formula, Y represents the predicted health status score, X1 represents the input blood glucose characteristic, X2 represents the input cholesterol characteristic, and X... n For the nth feature B0, B1, B... n is the regression coefficient, and ∈ is the error term.

5. The safety monitoring system for a limb assistive exercise device for critically ill patients according to claim 4, characterized in that, The analysis of user health data based on future health trends, combined with artificial intelligence algorithms, to assess user health risks specifically includes: A logistic regression machine learning classification model is used to assess user health risk based on predicted health trends. The risk assessment formula for logistic regression is as follows: In the formula, P(y=1|x) is the probability of the predicted event, y is the target variable, X is the input feature vector, w is the weight vector, x is a specific feature in the input feature vector X, b is the bias term, and exp is the exponential function.

6. The safety monitoring system for a limb assistive exercise device for critically ill patients according to claim 5, characterized in that, The data processing and analysis module specifically includes: The dynamic update unit for health risk: Based on new physical examination data and health information, the health risk assessment model is dynamically updated to reflect the latest health status and trends. Based on the SGD online learning algorithm, the model is updated in real time when new data is received, and the model is retrained regularly with new data. Results Interpretation and Feedback Unit: Generates a health report based on the results of the health risk assessment, and provides personalized health advice reports based on the user's lifestyle and dietary habits. The report output includes risk level, prediction of health status in the future period, and health intervention suggestions, including dietary adjustments, exercise recommendations, and regular physical examinations.

7. The safety monitoring system for a limb assistive exercise device for critically ill patients according to claim 6, characterized in that, The SGD-based online learning algorithm updates the model in real time upon receiving new data and periodically retrains the model using new data. include: The formula for the SGD online learning algorithm is as follows: In the formula, θ t These are the current model parameters, and δ is the learning rate, used to control the update step size. It is the gradient of the loss function L with respect to the model parameters θ, where θ t+1 These are the updated model parameters; Each time a new data point is received, the model is updated according to the above formula, so that the model can be adjusted in real time according to the new data. The model is also retrained in batches with new data periodically to update the entire model. Regularly collect and organize new health data, input the new dataset into the model, perform batch retraining through the standard SGD process, and readjust the model parameters based on the new training data.

8. The safety monitoring system for a limb assistive exercise device for critically ill patients according to claim 1, characterized in that, The health early warning module specifically includes: Health status assessment unit: Based on the results provided by the data processing and analysis module, including real-time vital signs data and historical physical examination data analysis results, assess the user's health status; The abnormality detection and monitoring unit sets health thresholds and compares the collected vital sign data with the set normal range in real time. If the data exceeds the normal range, an early warning is triggered. Early warning triggering unit: By interfacing with the anomaly detection unit, when an anomaly is detected, the early warning triggering unit will issue an early warning signal based on preset early warning standards and thresholds.

9. The safety monitoring system for a limb assistive exercise device for critically ill patients according to claim 8, characterized in that, The health early warning module also includes: Warning information transmission and notification unit: transmits warning information to patients, nursing staff and doctors, and notifies medical staff and patients of health warning information in real time according to the triggered warning level, and provides suggestions; Warning Level Assessment Unit: Based on the user's health status and data analysis results, different warning levels are assigned to each warning situation, and each warning level corresponds to different response measures; Response Response Recommendation Unit: Based on the type and urgency of the alert, this unit provides health advice, including temporary equipment shutdown, medical advice, and medication adjustments.

10. The safety monitoring system for a limb assistive exercise device for critically ill patients according to claim 1, characterized in that, The information display and feedback module specifically includes: Decision Support Unit: Based on early warning information and health assessment results, it provides response measures and decision support; Feedback and Interaction Unit: Interact with users, receive user feedback, adjust displayed content, and guide users to further understand the details of health advice; Data update and synchronization unit: updates users' health status and early warning data in real time, while keeping synchronized with the data processing module and the health early warning module.

Images